Please help with my data

[Nikole Day]

Hi friends, I'm a working on a project for my graduate studies and I'm just not a number cruncher by nature, I'm hoping that someone can help me to figure out how to make these numbers work.

Here is what I have and what I'm trying to do.

My data has a population of many students. It includes student demographics, academic information, and school information. What I am specifically looking at is the teachers associated with the students, the discipline and the demographics.

What I would like to do is take the teachers' years of experience (in years) and see if years of experience affect assignments of exclusionary discipline (represented in data as discipline received=1, not received=0). Then I would like to see if things like poverty, ESL, immigrant status, and disability affect this relationship. All of the variables are 1/0 as they are listed as either a yes/no piece of data meaning either the category applies or does not apply, with the exception of years of experience. I guess the problem in my mind is that years of experience is not the dependent variable so it being different is not convenient. I cannot figure out how to organize the data and run tests on it in a way that is logical and works. Please help me, I'm at my wits end!!

Thanks!

[Carlo Lazzaro]

Nikole:
whenever I read posts like yours I wonder where poster's supervisor/teacher/professor is.
Tha said:
1) you probably mean -logistic- or -logit-;
2) please read the FAQ on how to post mor effectively. Thanks.

[Nikole Day]

When I run a logit it tells me "no observations"

[Carlo Lazzaro]

Nikole:
have you already double- checked that this warning message is not due to:
1) missing values;
2) independent variables predicting the outcomes perfectly and subsequent omission of the related observations;
3) regressand=costant (i.e., always 0 or 1).

If no option of those reported above is on spot, please share an example/excerpt of your dataset via -dataex-, along with what you typed and what Stata gave you back (via CODE delimiters, please). Thanks.